feat: add github handle to member endpoints (IN-834) (#3742)

Signed-off-by: Gašper Grom <gasper.grom@gmail.com>

Author: gaspergrom

services/libs/tinybird/datasources/leaderboards_copy_ds.datasource

@@ -14,6 +14,7 @@ DESCRIPTION >
     - `previousPeriodValue` is the comparison metric from the previous period (0 for non-temporal leaderboards).
     - `collectionsSlugs` list of collection slugs the project belongs to.
     - `isLF` indicates whether the project is a LF project (1 = true, 0 = false).
+    - `githubHandle` is the GitHub username for contributor leaderboards (empty string for non-contributor leaderboards).
 
 TAGS "Analytics, Leaderboards, Project rankings"
 
@@ -28,7 +29,8 @@ SCHEMA >
     `value` Float64,
     `previousPeriodValue` Float64,
     `collectionsSlugs` Array(String),
-    `isLF` UInt8
+    `isLF` UInt8,
+    `githubHandle` String
 
 ENGINE MergeTree
 ENGINE_SORTING_KEY leaderboardType, rank, slug, id

services/libs/tinybird/datasources/members_sorted.datasource

@@ -13,6 +13,7 @@ DESCRIPTION >
     - `displayName` is the member's preferred display name across platforms.
     - `score` is the computed activity/engagement score for the member.
     - `publicName` is the denormalized public display name for efficient queries.
+    - `githubHandle` is the member's GitHub username from memberIdentities (empty string if not available).
 
 SCHEMA >
     `id` String,
@@ -29,7 +30,8 @@ SCHEMA >
     `updatedAt` DateTime64(3),
     `displayName` String,
     `score` Int32,
-    `publicName` String
+    `publicName` String,
+    `githubHandle` String
 
 ENGINE MergeTree
 ENGINE_PARTITION_KEY toYear(joinedAt)

services/libs/tinybird/pipes/contributor_dependency.pipe

@@ -14,7 +14,7 @@ DESCRIPTION >
     - `activity_type`: Optional string filter for single activity type (e.g., 'authored-commit')
     - `activity_types`: Optional array of activity types (e.g., ['authored-commit', 'co-authored-commit'])
     - `onlyContributions`: Optional boolean, defaults to 1 (contributions only), set to 0 for all activities
-    - Response: `id`, `displayName`, `contributionCount`, `contributionPercentage`, `roles`, `contributionPercentageRunningTotal`, `totalContributorCount`
+    - Response: `id`, `displayName`, `githubHandle`, `contributionCount`, `contributionPercentage`, `roles`, `contributionPercentageRunningTotal`, `totalContributorCount`
 
 NODE contributions_percentage_running_total
 SQL >
@@ -24,6 +24,7 @@ SQL >
             SELECT
                 id,
                 displayName,
+                githubHandle,
                 contributionCount,
                 contributionPercentage,
                 roles,

services/libs/tinybird/pipes/contributors_leaderboard.pipe

@@ -18,7 +18,7 @@ DESCRIPTION >
     - `offset`: Optional integer for result pagination, defaults to 0
     - Response:
     - Count mode (`count=true`): `count` (total number of contributors)
-    - Data mode (default): `id`, `avatar`, `displayName`, `contributionCount`, `contributionPercentage`, `roles`
+    - Data mode (default): `id`, `avatar`, `displayName`, `githubHandle`, `contributionCount`, `contributionPercentage`, `roles`
 
 NODE memberId_aggregates
 SQL >
@@ -55,6 +55,7 @@ SQL >
             m.id,
             m.avatar,
             case when is_non_lf.result then m.publicName else m.displayName end as displayName,
+            m.githubHandle,
             ma.contributionCount,
             ma.contributionPercentage,
             mr.roles

services/libs/tinybird/pipes/leaderboards_copy.pipe

@@ -1,53 +1,57 @@
 DESCRIPTION >
     Aggregates all individual leaderboard pipes into a single unified datasource for querying.
-    Consolidates 13 different leaderboard types with their respective rankings and values,
+    Consolidates 10 different leaderboard types with their respective rankings and values,
     and copies the results to a datasource on a daily schedule at 1 AM.
 
 NODE leaderboards_copy_union
 DESCRIPTION >
     Unions all leaderboard results with their respective type identifiers for consolidated querying
 
 SQL >
-    SELECT *, 'active-contributors' as leaderboardType
+    SELECT *, '' as githubHandle, 'active-contributors' as leaderboardType
     FROM leaderboards_project_active_contributors
     UNION ALL
-    SELECT *, 'active-organizations' as leaderboardType
+    SELECT *, '' as githubHandle, 'active-organizations' as leaderboardType
     FROM leaderboards_project_active_organizations
     UNION ALL
-    SELECT *, 'commit-activity' as leaderboardType
+    SELECT *, '' as githubHandle, 'commit-activity' as leaderboardType
     FROM leaderboards_commits
     UNION ALL
-    SELECT *, 'stars' as leaderboardType
+    SELECT *, '' as githubHandle, 'stars' as leaderboardType
     FROM leaderboards_stars
     UNION ALL
-    SELECT *, 'forks' as leaderboardType
+    SELECT *, '' as githubHandle, 'forks' as leaderboardType
     FROM leaderboards_forks
     UNION ALL
-    SELECT *, 'package-downloads' as leaderboardType
+    SELECT *, '' as githubHandle, 'package-downloads' as leaderboardType
     FROM leaderboards_package_downloads
     UNION ALL
-    SELECT *, 0.0 as previousPeriodValue, 'focused-teams' as leaderboardType
+    SELECT *, 0.0 as previousPeriodValue, '' as githubHandle, 'focused-teams' as leaderboardType
     FROM leaderboards_avg_commits_per_author
     UNION ALL
-    SELECT *, 0.0 as previousPeriodValue, 'small-teams-massive-output' as leaderboardType
+    SELECT
+        *,
+        0.0 as previousPeriodValue,
+        '' as githubHandle,
+        'small-teams-massive-output' as leaderboardType
     FROM leaderboards_small_project_commit
     UNION ALL
-    SELECT *, 0.0 as previousPeriodValue, 'codebase-size' as leaderboardType
+    SELECT *, 0.0 as previousPeriodValue, '' as githubHandle, 'codebase-size' as leaderboardType
     FROM leaderboards_codebase_size
     UNION ALL
-    SELECT *, 'fastest-mergers' as leaderboardType
+    SELECT *, '' as githubHandle, 'fastest-mergers' as leaderboardType
     FROM leaderboards_merge_time
     UNION ALL
-    SELECT *, 'fastest-responders' as leaderboardType
+    SELECT *, '' as githubHandle, 'fastest-responders' as leaderboardType
     FROM leaderboards_issue_response
     UNION ALL
-    SELECT *, 0.0 as previousPeriodValue, 'resolution-rate' as leaderboardType
+    SELECT *, 0.0 as previousPeriodValue, '' as githubHandle, 'resolution-rate' as leaderboardType
     FROM leaderboards_resolution_rate
     UNION ALL
     SELECT *, 'contributors' as leaderboardType
     FROM leaderboards_members
     UNION ALL
-    SELECT *, 'organizations' as leaderboardType
+    SELECT *, '' as githubHandle, 'organizations' as leaderboardType
     FROM leaderboards_organizations
 
 TYPE COPY

services/libs/tinybird/pipes/leaderboards_members.pipe

@@ -8,7 +8,7 @@ DESCRIPTION >
     Retrieves all members from the populated datasource
 
 SQL >
-    SELECT id, displayName, avatar FROM members_sorted
+    SELECT id, displayName, avatar, githubHandle FROM members_sorted
 
 NODE leaderboards_member_activity_types
 DESCRIPTION >
@@ -66,13 +66,15 @@ SQL >
         arrayDistinct(arrayFlatten(groupArray(proj.collectionsSlugs))) as collectionSlugs,
         0 as isLF,
         cast(coalesce(c.memberActivityCount, 0) as Float64) as value,
-        cast(coalesce(pp.memberActivityCount, 0) as Float64) as previousPeriodValue
+        cast(coalesce(pp.memberActivityCount, 0) as Float64) as previousPeriodValue,
+        p.githubHandle as githubHandle
     FROM leaderboards_members_data p
     INNER JOIN leaderboards_members_current_period c ON p.id = c.memberId
     LEFT JOIN leaderboards_members_previous_period pp ON p.id = pp.memberId ARRAY
     JOIN c.segmentIds as sid
     LEFT JOIN leaderboards_members_projects proj ON proj.segmentId = sid
     WHERE c.memberActivityCount > 0
-    GROUP BY p.id, p.displayName, p.avatar, c.memberActivityCount, pp.memberActivityCount
+    GROUP BY
+        p.id, p.displayName, p.avatar, p.githubHandle, c.memberActivityCount, pp.memberActivityCount
     ORDER BY value DESC
     LIMIT 100

services/libs/tinybird/pipes/members_sorted_copy_pipe.pipe

@@ -1,16 +1,24 @@
 DESCRIPTION >
     Filters out `isBot = true` and `isTeamMember=true` members. Also possible to use more granular sorting keys in the destination datasource `members_sorted` Copy pipe runs every hour
 
+NODE github_usernames
+SQL >
+    SELECT memberId, argMax(value, createdAt) AS githubHandle
+    FROM memberIdentities FINAL
+    WHERE platform = 'github' AND type = 'username'
+    GROUP BY memberId
+
 NODE members_pre_filter
 SQL >
-    SELECT members.*, pub.publicName
-    FROM members final
-    left join members_public_names_ds pub on pub.memberId = members.id
-    where
-        not isBot
-        and not isTeamMember
-        and not isOrganization
-        and members.id in (select distinct memberId from activityRelations)
+    SELECT members.*, pub.publicName, coalesce(gh.githubHandle, '') AS githubHandle
+    FROM members FINAL
+    LEFT JOIN members_public_names_ds pub ON pub.memberId = members.id
+    LEFT JOIN github_usernames gh ON gh.memberId = members.id
+    WHERE
+        NOT isBot
+        AND NOT isTeamMember
+        AND NOT isOrganization
+        AND members.id IN (SELECT DISTINCT memberId FROM activityRelations)
 
 TYPE COPY
 TARGET_DATASOURCE members_sorted